© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30933
    Prev
    Next
    INDEX
    Explanations

    ground

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decrement
    -0.08
     scaling
    -0.08
    STEP
    -0.08
    _steps
    -0.08
    ergy
    -0.08
    _STEP
    -0.08
    isting
    -0.08
    消防
    -0.08
    istič
    -0.08
    	step
    -0.08
    POSITIVE LOGITS
     shredded
    0.09
     forehead
    0.08
    OE
    0.08
     ashes
    0.08
    anii
    0.08
     raven
    0.08
     flax
    0.07
     Mat
    0.07
     horny
    0.07
     Verein
    0.07
    Activations Density 0.002%

    No Known Activations